Remote STEM Researcher – AI Evaluation

About the role

We are seeking a highly qualified STEM researcher to join a leading technology company on a full‑time remote basis. The role focuses on designing and solving challenging STEM problems that probe the limits of large language models, contributing to cutting‑edge AI evaluation research.

Key responsibilities

• Design and solve complex STEM problems to test large language model capabilities.
• Create clear, step‑by‑step solutions with well‑articulated reasoning.
• Collaborate with LLM researchers to align problems with evaluation goals, especially in abstraction, multi‑step reasoning, and symbolic manipulation.
• Help define new evaluation benchmarks based on physics curricula ranging from early undergraduate to PhD‑level topics.
• Leverage AI tools to enhance analytical capabilities and support future‑proof career growth.

Required profile

• Advanced degree (Ph.D., post‑doctoral, or Master’s) in a STEM discipline.
• Strong analytical ability and experience with graduate‑level STEM concepts.
• Proven skill in breaking down complex technical ideas into clear explanations.
• Creative, lateral thinking and self‑motivation for independent remote work.
• Excellent structured communication and collaboration skills in a virtual environment.

Required skills

What we offer

• Competitive compensation based on experience.
• Fully remote work from anywhere.
• Opportunity to influence AI evaluation standards at a global technology leader.